# FTSCommDetector: Discovering Behavioral Communities through Temporal Synchronization

arXiv: https://arxiv.org/abs/2510.00014 · HTML: https://mlsanity.com/paper/2510.00014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Attributed Graph Clustering: A Deep Attentional Embedding Approach](https://mlsanity.com/paper/1906.06532/) (2019)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors](https://mlsanity.com/paper/2305.18803/) (2023)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [Cluster-guided Contrastive Graph Clustering Network](https://mlsanity.com/paper/2301.01098/) (2023)
- [Deep Temporal Graph Clustering](https://mlsanity.com/paper/2305.10738/) (2023)
- [DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization](https://mlsanity.com/paper/2312.12697/) (2023)
- [LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering](https://mlsanity.com/paper/2405.11801/) (2024)
- [Graph-based Time Series Clustering for End-to-End Hierarchical Forecasting](https://mlsanity.com/paper/2305.19183/) (2023)
- [VGAER: Graph Neural Network Reconstruction based Community Detection](https://mlsanity.com/paper/2201.04066/) (2022)
- [Time Series Clustering With Random Convolutional Kernels](https://mlsanity.com/paper/2305.10457/) (2023)
- [Amortized Probabilistic Detection of Communities in Graphs](https://mlsanity.com/paper/2010.15727/) (2020)

## Abstract (arXiv)

Why do trillion-dollar tech giants AAPL and MSFT diverge into different response patterns during market disruptions despite identical sector classifications? This paradox reveals a fundamental limitation: traditional community detection methods fail to capture synchronization-desynchronization patterns where entities move independently yet align during critical moments. To this end, we introduce FTSCommDetector, implementing our Temporal Coherence Architecture (TCA) to discover similar and dissimilar communities in continuous multivariate time series. Unlike existing methods that process each timestamp independently, causing unstable community assignments and missing evolving relationships, our approach maintains coherence through dual-scale encoding and static topology with dynamic attention. Furthermore, we establish information-theoretic foundations demonstrating how scale separation maximizes complementary information and introduce Normalized Temporal Profiles (NTP) for scale-invariant evaluation. As a result, FTSCommDetector achieves consistent improvements across four diverse financial markets (SP100, SP500, SP1000, Nikkei 225), with gains ranging from 3.5% to 11.1% over the strongest baselines. The method demonstrates remarkable robustness with only 2% performance variation across window sizes from 60 to 120 days, making dataset-specific tuning unnecessary, providing practical insights for portfolio construction and risk management.